求高手,模拟浏览器抓取网页
如抓取http://map.sogou.com/api/这个网页,我写的程序,如果不带网址后面的"/",会抓取得不到,但是站上网(http://tool.chinaz.com/Tools/PageCode.aspx),不带最后面的"/"即可抓取到(即:http://map.sogou.com/api),他是什么原理?下面贴出我的代码,请改进
<br /> <br /> function file_get($url){<br /> ob_start();<br /> $ch = curl_init();<br /> <br /> curl_setopt($ch, CURLOPT_COOKIEJAR, "./cookie.txt");<br /> curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 2.0.50727; InfoPath.1; CIBA)");<br /> curl_setopt($ch, CURLOPT_URL, $url);<br /> curl_setopt($ch, CURLOPT_HEADER, FALSE);<br /> curl_setopt($ch, CURLOPT_COOKIESESSION, TRUE);<br /> curl_setopt($ch, CURLOPT_NOBODY, FALSE);<br /> <br /> curl_exec($ch);<br /> curl_close($ch);<br /> $content = ob_get_clean();<br /> <br /> <br /> <br /> return $content;<br /> <br /> }<br />